Databricks Certified Generative AI Engineer Associate — Question 78

A Generative AI Engineer is developing an LLM application to interact with users to provide personalized movie recommendations.

Given the potential for malicious user inputs, which technique would be most effective in safeguarding the application?

Answer options

• A. Reduce the time that the users can interact with the LLM
• B. Increase the amount of compute that powers the LLM to process input faster
• C. Ask the LLM to remind the user that the input is malicious but continue the conversation with the user
• D. Implement a safety filter that detects any harmful inputs and ask the LLM to respond that it is unable to assist

Correct answer: D

Explanation

The correct answer is D because implementing a safety filter is essential for identifying harmful inputs and ensuring the application remains secure. Options A and B do not directly address the issue of malicious inputs, while option C could potentially allow harmful content to be processed, which does not safeguard the application.